Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     берег
    -0.06
    .TabStop
    -0.06
     greeting
    -0.06
    chief
    -0.06
     Converts
    -0.06
    _Default
    -0.06
     urging
    -0.06
     proč
    -0.06
     ره
    -0.06
    _deleted
    -0.06
    POSITIVE LOGITS
     beautifully
    0.07
    ((_
    0.07
    θ
    0.07
    .fs
    0.06
    ταση
    0.06
    embali
    0.06
     найбіль
    0.06
     passer
    0.06
    母
    0.06
     Shim
    0.06
    Act Density 0.001%

    No Known Activations